Find and Import Data
all_files <- list.files()
csv_files <- list.files(pattern = "\\.csv$", ignore.case = TRUE)
print(all_files)
## [1] "bank.csv"
## [2] "Chapter 12 - Watching Competitors.pdf"
## [3] "desktop.ini"
## [4] "DodgersData.csv"
## [5] "grapeJuice (1).csv"
## [6] "grapeJuice.csv"
## [7] "MKTG 4000 - Group 2 Survey_April 15, 2026_16.21.csv"
## [8] "MKTG+4000+-+Group+2+Survey_April+15,+2026_16.21"
## [9] "MKTG+4000+-+Group+2+Survey_April+15,+2026_16.21.zip"
## [10] "Screenshot 2026-03-04 161737.png"
## [11] "syntax - t-test.txt"
## [12] "textbook_platform_analysis (1).Rmd"
## [13] "textbook_platform_analysis.Rmd"
## [14] "textbook_platform_analysis_autofind_csv.Rmd"
print(csv_files)
## [1] "bank.csv"
## [2] "DodgersData.csv"
## [3] "grapeJuice (1).csv"
## [4] "grapeJuice.csv"
## [5] "MKTG 4000 - Group 2 Survey_April 15, 2026_16.21.csv"
target_file <- "MKTG 4000 - Group 2 Survey_April 15, 2026_16.21.csv"
if (target_file %in% csv_files) {
survey_file <- target_file
} else if (length(csv_files) >= 1) {
survey_file <- csv_files[1]
} else {
stop("No CSV file was found in your project folder. Upload your survey CSV into the same Posit Cloud project as this .Rmd file.")
}
survey_raw <- read.csv(survey_file, stringsAsFactors = FALSE)
survey <- survey_raw[-c(1,2), ] %>%
clean_names() %>%
rename(
academic_status = q1,
textbook_format = q2,
user_friendly = q3,
purchase_pref = q4,
other_platform = q5,
spending = q6,
price_perception = q7
) %>%
mutate(
academic_status = recode(academic_status, "Sophmore" = "Sophomore"),
across(everything(), trimws)
)
Data Check
head(survey)
## start_date end_date status ip_address progress
## 3 2026-03-23 16:03:17 2026-03-23 16:04:12 IP Address 136.168.214.221 100
## 4 2026-03-23 16:04:02 2026-03-23 16:04:53 IP Address 136.168.214.222 100
## 5 2026-03-23 16:42:25 2026-03-23 16:43:14 IP Address 136.168.55.238 100
## 6 2026-03-25 16:47:32 2026-03-25 16:48:59 IP Address 136.168.214.250 100
## 7 2026-04-08 16:22:23 2026-04-08 16:25:57 IP Address 136.168.214.221 100
## 8 2026-04-08 16:29:29 2026-04-08 16:30:03 IP Address 136.168.214.236 100
## duration_in_seconds finished recorded_date response_id
## 3 55 True 2026-03-23 16:04:13 R_1Wxx2PnUIHxzjO6
## 4 51 True 2026-03-23 16:04:53 R_3nYJdpmkLal6m1P
## 5 48 True 2026-03-23 16:43:15 R_1pefVBQWLQl73hf
## 6 86 True 2026-03-25 16:48:59 R_7QKE8qLhktJR321
## 7 214 True 2026-04-08 16:25:59 R_6mkmStYyf2Lpjrj
## 8 34 True 2026-04-08 16:30:04 R_70NOV29NJLyWCFD
## recipient_last_name recipient_first_name recipient_email external_reference
## 3
## 4
## 5
## 6
## 7
## 8
## location_latitude location_longitude distribution_channel user_language
## 3 35.3044 -119.1031 anonymous EN
## 4 35.3044 -119.1031 anonymous EN
## 5 35.3288 -118.9748 anonymous EN
## 6 35.3044 -119.1031 anonymous EN
## 7 35.3878 -118.936 anonymous EN
## 8 35.3878 -118.936 anonymous EN
## academic_status textbook_format user_friendly purchase_pref
## 3 Senior electronic McGraw Hill McGraw Hill
## 4 Senior electronic Pearson I don't have a preference
## 5 Senior electronic McGraw Hill Pearson
## 6 Senior electronic Pearson I don't have a preference
## 7 Senior electronic McGraw Hill McGraw Hill
## 8 Junior electronic Pearson I don't have a preference
## other_platform spending price_perception
## 3 N/A $50-$75 They are about the same
## 4 N/A less than $50 I don't pay attention to textbook prices
## 5 n/a less than $50 Pearson is more expensive
## 6 $75-$100 They are about the same
## 7 N/A $50-$75 They are about the same
## 8 less than $50 McGraw Hill is more expensive
## q_ballot_box_stuffing
## 3
## 4
## 5
## 6
## 7
## 8
nrow(survey)
## [1] 27
Graph 1: Preferred Textbook Format
survey %>%
count(textbook_format) %>%
ggplot(aes(x = textbook_format, y = n, fill = textbook_format)) +
geom_col(show.legend = FALSE) +
geom_text(aes(label = n), vjust = -0.3) +
labs(title = "Preferred Textbook Format", x = "Format", y = "Responses") +
theme_minimal()
Graph 3: Purchase Preference
survey %>%
count(purchase_pref) %>%
ggplot(aes(x = purchase_pref, y = n, fill = purchase_pref)) +
geom_col(show.legend = FALSE) +
geom_text(aes(label = n), hjust = -0.2) +
coord_flip() +
labs(title = "Preferred Platform for Purchasing Textbooks", x = "", y = "Responses") +
theme_minimal()
Graph 4: Expected Spending
survey %>%
count(spending) %>%
ggplot(aes(x = spending, y = n, fill = spending)) +
geom_col(show.legend = FALSE) +
geom_text(aes(label = n), vjust = -0.3) +
labs(title = "Expected Spending Per Textbook", x = "Spending Range", y = "Responses") +
theme_minimal()
Graph 5: Price Perception
survey %>%
count(price_perception) %>%
ggplot(aes(x = price_perception, y = n, fill = price_perception)) +
geom_col(show.legend = FALSE) +
geom_text(aes(label = n), hjust = -0.2) +
coord_flip() +
labs(title = "Which Platform Seems More Expensive?", x = "", y = "Responses") +
theme_minimal()
